© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13909
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.70
    SizeMode
    -0.69
     resourceCulture
    -0.67
    findpost
    -0.65
     ब्रेकडाउन
    -0.61
     MonoBehaviour
    -0.60
     phénom
    -0.60
     avulla
    -0.59
     compréhen
    -0.59
     effectivement
    -0.58
    POSITIVE LOGITS
    XmlEnum
    0.66
     propOrder
    0.56
     crocodile
    0.49
    Where
    0.48
     jaguar
    0.47
     tumours
    0.47
    ranton
    0.47
     ammon
    0.46
    Wire
    0.45
    thâu
    0.45
    Activations Density 0.020%

    No Known Activations